To the Max: Reinventing Reward in Reinforcement Learning

Documenti analoghi

• You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization
  di: Veviurko, Grigorii, et al.
  Pubblicazione: (2023)
• A Penalty-Based Guardrail Algorithm for Non-Decreasing Optimization with Inequality Constraints
  di: Stepanovic, Ksenija, et al.
  Pubblicazione: (2024)
• Sufficient Decision Proxies for Decision-Focused Learning
  di: Schutte, Noah, et al.
  Pubblicazione: (2025)
• Diverse Projection Ensembles for Distributional Reinforcement Learning
  di: Zanger, Moritz A., et al.
  Pubblicazione: (2023)
• Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
  di: Tamassia, Isidoro, et al.
  Pubblicazione: (2025)